Výsledky vyhledávání - "Yang, Yuhuan"

Report

ReMamber: Referring Image Segmentation with Mamba Twister

Autor: Yang, Yuhuan, Ma, Chaofan, Yao, Jiangchao, Zhong, Zhun, Zhang, Ya, Wang, Yanfeng

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language

Externí odkaz: http://arxiv.org/abs/2403.17839

Zobrazit plný text záznamu

Report

AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

Autor: Ma, Chaofan, Yang, Yuhuan, Ju, Chen, Zhang, Fei, Zhang, Ya, Wang, Yanfeng

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic assumptions in

Externí odkaz: http://arxiv.org/abs/2309.00096

Zobrazit plný text záznamu

Report

Multi-Modal Prototypes for Open-World Semantic Segmentation

Autor: Yang, Yuhuan, Ma, Chaofan, Ju, Chen, Zhang, Fei, Yao, Jiangchao, Zhang, Ya, Wang, Yanfeng

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either providing

Externí odkaz: http://arxiv.org/abs/2307.02003

Zobrazit plný text záznamu

Report

DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery

Autor: Ma, Chaofan, Yang, Yuhuan, Ju, Chen, Zhang, Fei, Liu, Jinxiang, Wang, Yu, Zhang, Ya, Wang, Yanfeng

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we pro

Externí odkaz: http://arxiv.org/abs/2303.09813

Zobrazit plný text záznamu

Report

Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models

Autor: Ma, Chaofan, Yang, Yuhuan, Wang, Yanfeng, Zhang, Ya, Xie, Weidi

When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the pre-trained

Externí odkaz: http://arxiv.org/abs/2210.15138

Zobrazit plný text záznamu

Report

Transforming the Interactive Segmentation for Medical Imaging

Autor: Liu, Wentao, Ma, Chaofan, Yang, Yuhuan, Xie, Weidi, Zhang, Ya

The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example

Externí odkaz: http://arxiv.org/abs/2208.09592

Zobrazit plný text záznamu